2D Keypoints
2D Semantic Segmentation
License: Custom


Look into Person (LIP) is a new large-scale dataset, focus on semantic understanding of person. Following are the detailed descriptions.

1.1 Volume

The dataset contains 50,000 images with elaborated pixel-wise annotations with 19 semantic human part labels and 2D human poses with 16 key points.

1.2 Diversity

The annotated 50,000 images are cropped person instances from COCO dataset with size larger than 50 * 50.The images collected from the real-world scenarios contain human appearing with challenging poses and views, heavily occlusions, various appearances and low-resolutions. We are working on collecting and annotating more images to increase diversity.

Data Collection

Single Person

We have divided images into three sets. 30462 images for training set, 10000 images for validation set and 10000 for testing set.

Besides we have another large dataset mentioned in "Human parsing with contextualized convolutional neural network." ICCV'15, which focuses on fashion images. You can download the dataset including 17000 images as extra training data.


To stimulate the multiple-human parsing research, we collect the images with multiple person instances to establish the first standard and comprehensive benchmark for instance-level human parsing. Our Crowd Instance-level Human Parsing Dataset (CIHP) contains 28280 training, 5000 validation and 5000 test images, in which there are 38280 multiple-person images in total.

Video Multi-Person Human Parsing

VIP(Video instance-level Parsing) dataset, the first video multi-person human parsing benchmark, consists of 404 videos covering various scenarios. For every 25 consecutive frames in each video, one frame is annotated densely with pixel-wise semantic part categories and instance-level identification. There are 21247 densely annotated images in total. We divide these 404 sequences into 304 train sequences, 50 validation sequences and 50 test sequences.

  • VIP_Fine: All annotated images and fine annotations for train and val sets.
  • VIP_Sequence: 20-frame surrounding each VIP_Fine image (-10 | +10).
  • VIP_Videos: 404 video sequences of VIP dataset.

Image-based Multi-pose Virtual Try On

MPV (Multi-Pose Virtual try on) dataset, which consists of 35,687/13,524 person/clothes images, with the resolution of 256x192. Each person has different poses. We split them into the train/test set 52,236/10,544 three-tuples, respectively.


  title={Instance-level human parsing via part grouping network},
  author={Gong, Ke and Liang, Xiaodan and Li, Yicheng and Chen, Yimin and Yang, Ming and Lin,
  booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
  title={Look into person: Self-supervised structure-sensitive learning and a new
benchmark for human parsing},
  author={Gong, Ke and Liang, Xiaodan and Zhang, Dongyu and Shen, Xiaohui and Lin, Liang},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  title={Adaptive temporal encoding network for video instance-level human parsing},
  author={Zhou, Qixian and Liang, Xiaodan and Gong, Ke and Lin, Liang},
  booktitle={Proceedings of the 26th ACM international conference on Multimedia},
  title={Look into person: Joint body parsing \& pose estimation network and a new benchmark},
  author={Liang, Xiaodan and Gong, Ke and Shen, Xiaohui and Lin, Liang},
  journal={IEEE transactions on pattern analysis and machine intelligence},
  title={Human parsing with contextualized convolutional neural network},
  author={Liang, Xiaodan and Xu, Chunyan and Shen, Xiaohui and
Yang, Jianchao and Liu, Si and Tang, Jinhui and Lin, Liang and Yan, Shuicheng},
  booktitle={Proceedings of the IEEE international conference on computer vision},



Data Summary
Provided by
Liang Lin
I am a full Professor of Sun Yat-sen University (SYSU) and a researcher in AI. I am supervising the HCP-I2 Lab: Human-Cyber-Physical Intelligence Integration, SYSU.
Start Building AI Now